© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 11287
    Prev
    Next
    INDEX
    Explanations

    past participles and usages indicating prior occurrences or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hentet
    -0.52
     numériques
    -0.50
     copertina
    -0.49
    initComponents
    -0.47
     llanto
    -0.47
     européens
    -0.47
    ovina
    -0.46
    věr
    -0.46
    BERS
    -0.45
     oldu
    -0.44
    POSITIVE LOGITS
    省市镇
    0.88
    oa̍t
    0.69
     habían
    0.67
     GENERATED
    0.67
     hadn
    0.67
    UnknownFields
    0.66
    ніципа
    0.65
    IVEREF
    0.65
    IsMutable
    0.62
     Había
    0.62
    Activations Density 0.512%

    No Known Activations